FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting

TL;DR

FAF is a novel framework that combines meta-learning and task-specific modules to improve few-shot time series forecasting, effectively leveraging generalized and local features for better accuracy in data-scarce scenarios.

Contribution

The paper introduces FAF, a feature-adaptive framework with a meta-learned generalized module and task-specific regions, enhancing few-shot forecasting performance.

Findings

FAF outperforms baseline methods on five real-world datasets.

Achieves 41.81% improvement over iTransformer on CO2 emissions data.

Demonstrates robustness and personalization in sparse data conditions.

Abstract

Multi-task and few-shot time series forecasting tasks are commonly encountered in scenarios such as the launch of new products in different cities. However, traditional time series forecasting methods suffer from insufficient historical data, which stems from a disregard for the generalized and specific features among different tasks. For the aforementioned challenges, we propose the Feature-Adaptive Time Series Forecasting Framework (FAF), which consists of three key components: the Generalized Knowledge Module (GKM), the Task-Specific Module (TSM), and the Rank Module (RM). During training phase, the GKM is updated through a meta-learning mechanism that enables the model to extract generalized features across related tasks. Meanwhile, the TSM is trained to capture diverse local dynamics through multiple functional regions, each of which learns specific features from individual tasks. During testing phase, the RM dynamically selects the most relevant functional region from the TSM based on input sequence features, which is then combined with the generalized knowledge learned by the GKM to generate accurate forecasts. This design enables FAF to achieve robust and personalized forecasting even with sparse historical observations We evaluate FAF on five diverse real-world datasets under few-shot time series forecasting settings. Experimental results demonstrate that FAF consistently outperforms baselines that include three categories of time series forecasting methods. In particular, FAF achieves a 41.81\% improvement over the best baseline, iTransformer, on the CO$_2$ emissions dataset.